© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 42876
    Prev
    Next
    INDEX
    Explanations

    arguments and claims related to social issues and policy changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    87
    +0.30
    1.5%
    481
    +0.19
    1.0%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.30
    -0.02
    263
    +0.19
    0.04
    59
    +0.12
    0.03
    Negative Logits
    )?
    -0.64
    ?'
    -0.63
     Pwr
    -0.59
    amination
    -0.59
     COURT
    -0.57
    soType
    -0.57
    agar
    -0.57
    quished
    -0.56
    aign
    -0.56
    externalActionCode
    -0.55
    POSITIVE LOGITS
     "#
    0.88
     "[
    0.87
     "âĢ¦
    0.86
     "...
    0.74
     "'
    0.70
     "
    0.64
     widespread
    0.55
     ""
    0.53
     "@
    0.53
     purported
    0.53
    Activations Density 0.591%

    No Known Activations